# EGG: a toolkit for research on Emergence of lanGuage in Games

**Authors:** Eugene Kharitonov, Rahma Chaabouni, Diane Bouchacourt, Marco, Baroni

arXiv: 1907.00852 · 2019-10-15

## TL;DR

EGG is a modular toolkit designed to facilitate research on emergent language in neural agents, simplifying the creation and optimization of communication games to advance understanding of language evolution and AI development.

## Contribution

The paper introduces EGG, a flexible, modular toolkit that streamlines the implementation and experimentation of emergent language communication games.

## Key findings

- Simplifies the development of emergent language experiments
- Enables easy customization of communication game architectures
- Aims to lower technical barriers for researchers

## Abstract

There is renewed interest in simulating language emergence among deep neural agents that communicate to jointly solve a task, spurred by the practical aim to develop language-enabled interactive AIs, as well as by theoretical questions about the evolution of human language. However, optimizing deep architectures connected by a discrete communication channel (such as that in which language emerges) is technically challenging. We introduce EGG, a toolkit that greatly simplifies the implementation of emergent-language communication games. EGG's modular design provides a set of building blocks that the user can combine to create new games, easily navigating the optimization and architecture space. We hope that the tool will lower the technical barrier, and encourage researchers from various backgrounds to do original work in this exciting area.

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/1907.00852/full.md

## Figures

9 figures with captions in the complete paper: https://tomesphere.com/paper/1907.00852/full.md

## References

26 references — full list in the complete paper: https://tomesphere.com/paper/1907.00852/full.md

---
Source: https://tomesphere.com/paper/1907.00852